{"id":"W4402671446","doi":"10.18653/v1/2024.arabicnlp-1.27","title":"Dallah: A Dialect-Aware Multimodal Large Language Model for Arabic","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Arabic; Computer science; Natural language processing; Linguistics; Artificial intelligence; Speech recognition; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002462143,0.0001531805,0.0001342429,0.0001375292,0.0000884235,0.0003601817,0.0007629377,0.00009354773,0.00001884555],"category_scores_gemma":[0.0000547692,0.0001172307,0.0001018494,0.0002927821,0.00001634392,0.0005788974,0.0002380036,0.0001624388,0.00003192061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004993923,"about_ca_system_score_gemma":0.0001062664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002254872,"about_ca_topic_score_gemma":0.00004332262,"domain_scores_codex":[0.9988436,0.00001630252,0.0001507879,0.0004613952,0.0001764472,0.0003514647],"domain_scores_gemma":[0.9993516,0.0001019866,0.00002101246,0.000397237,0.00005985963,0.00006829925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001685431,0.0001252751,0.00002405073,0.0004884817,0.00005296925,0.0001485435,0.00884553,0.0001942946,0.02085069,0.8092487,0.02181384,0.1381908],"study_design_scores_gemma":[0.0001256368,0.00002042373,0.000001513975,0.00004454049,0.000005197537,0.00001046993,0.00001665867,0.9606939,0.01122124,0.02692701,0.0007500336,0.0001833782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008924898,0.003494388,0.9905609,0.0009209196,0.0001749853,0.0002716951,0.00002328991,0.003056791,0.0006045505],"genre_scores_gemma":[0.5290562,0.000004043141,0.4675159,0.0003764029,0.00006484469,0.00006043275,0.000008048577,0.00001520169,0.002898935],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9604996,"threshold_uncertainty_score":0.4780528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01374668446138967,"score_gpt":0.304899655221933,"score_spread":0.2911529707605433,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}